Back to plugin

Security audit

Venice OpenClaw provider

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a conditional prompt-injection weakness in how some historical tool results are represented, but the verdict is benign because the reported behavior is a compatibility fallback rather than evidence of intentional harm.

The verdict is benign, but the finding describes a conditional weakness that could let attacker-controlled tool output influence a model during a specific history replay. Consider whether you use that replay path and what tools the agent can access; the scanner says any further impact depends on model behavior and gateway controls.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

MCP06

Warning
Location
plugin/dist/stream.js:61
Finding

Historical Tool Results Promoted to User Messages Enable Prompt Injection ## Remediation Suggestions 1. **Preserve tool-output provenance.** Use a provider-supported representation that retains the distinction between tool data and user instructions. Do not assign raw tool results to the `user` role. 2. **Fail safely when history cannot be represented.** If unsigned tool history is incompatible with the provider, omit the affected call/result batch with an explicit diagnostic, or reject the replay. Do not silently promote its contents to user input. 3. **Treat textual framing as defense in depth only.** If a textual fallback is unavoidable, clearly identify external content as untrusted, use structured encoding, and add trusted instructions prohibiting its interpretation as commands. These measures do not replace protocol-level role separation. 4. **Retain independent action controls.** Require authorization for sensitive tool actions regardless of model instructions, particularly filesystem writes, command execution, credential access, and outbound data transfers. 5. **Add regression coverage.** Test unsigned Gemini 3 history containing malicious tool results, including delimiter-breaking text and requests for sensitive actions. Assert that attacker-controlled output is never emitted as a user-role message. Also verify that signed history retains the intended tool-call associations.

Content
View full analysis

Vulnerability Details

File Location: plugin/dist/stream.js:61–77, applyVeniceGeminiToolHistoryCompatibility
Vulnerability Type: Prompt injection through loss of tool-output provenance
Risk Level: Medium

Vulnerable Code

javascript
		if (record.role === "tool") {
			const toolCallId = typeof record.tool_call_id === "string" ? record.tool_call_id : void 0;
			if (!toolCallId) continue;
			const pendingCalls = pendingDowngradedToolCalls;
			if (!pendingCalls) continue;
			const toolNames = pendingCalls.get(toolCallId);
			if (!toolNames) continue;
			const toolName = toolNames.shift();
			if (!toolName) continue;
			if (toolNames.length === 0) pendingCalls.delete(toolCallId);
			const result = stringifyHistoricalValue(record.content);
			for (const key of Object.keys(record)) delete record[key];
			record.role = "user";
			record.content = `[Historical tool result for ${toolName}:\n${result}]`;
			continue;
		}

Technical Analysis

The stream wrapper implements a compatibility fallback for Venice Gemini 3 models. When a historical tool-call batch lacks a matching thought signature, it converts the batch into textual history. Associated tool results are then rewritten from tool messages into user messages.

The vulnerable segment copies tool-result content verbatim, deletes the original message fields, and assigns record.role = "user". This removes structured tool provenance and places potentially attacker-controlled data in a role normally reserved for user input.

The surrounding [Historical tool result ...] label provides contextual guidance but does not enforce a security boundary. Instructions embedded in the result remain part of a user-role message.

This is a conditional prompt-injection weakness, not evidence of intentional malicious behavior. Exploitation requires attacker-controlled tool output and replay through the affected compatibility fallback.

Attack Path

  1. An attacker controls content consumed by a ...[truncated 1736 chars]

SkillSpector was not run because this plugin release contains no bundled skills.

Endor dependency reachability

Checked Nov 16, 2026 · 2:36 AM UTC

No reachable vulnerabilities reported

Endor dependency scan completed.